Goldsky (Web3 Data Indexing & Subgraphs)

Goldsky (Web3 Data Indexing & Subgraphs) MCP Connector for Claude

A+

Manage Web3 data pipelines and subgraphs. List, create, and monitor real-time indexing pipelines directly from your AI agent.

12 tools Official Updated Jun 28, 2026 Official Vinkius Partner

Connect your Goldsky account to any AI agent to orchestrate high-performance Web3 data pipelines through natural language. Goldsky provides the infrastructure to index blockchain data in real-time, and this MCP server puts that power in your chat interface.

What you can do

  • Pipeline Management — List all active Turbo pipelines, create new ones from JSON definitions, and delete obsolete ones.
  • Lifecycle Control — Pause, resume, or restart pipelines instantly to manage resource usage or apply updates.
  • Real-time Monitoring — Fetch execution logs, check runtime status (running, paused, failed), and inspect internal pipeline states.
  • Error Tracking — Query error counts within specific time windows to ensure your data indexing remains healthy.
  • Validation — Validate pipeline definitions (sources, transforms, sinks) before deployment to prevent configuration errors.

How it works

  1. Subscribe to this server
  2. Enter your Goldsky API Key
  3. Start managing your Web3 data infrastructure from Claude, Cursor, or any MCP client

Who is this for?

  • Web3 Developers — Deploy and debug subgraphs and pipelines without leaving your code editor.
  • Data Engineers — Monitor indexing health and retrieve logs to troubleshoot data flow issues in real-time.
  • Protocol Teams — Manage cross-chain data indexing infrastructure through simple conversational commands.
web3subgraphsdata-indexingethereumreal-time-data

12 tools expose this connector's capabilities to your AI agent.

create_pipeline

Create and deploy a new pipeline

delete_pipeline

Delete a pipeline (irreversible)

get_pipeline_error_count

Get error count in a time window for a pipeline

get_pipeline_logs

Retrieve execution logs for a pipeline

get_pipeline_state

Get internal state of a pipeline

get_pipeline_status

g., running, paused, failed) of a pipeline. Get current runtime status of a pipeline

get_pipeline

Get details of a specific pipeline

list_pipelines

List all pipelines in the project

pause_pipeline

Pause a running pipeline

restart_pipeline

Restart a pipeline

resume_pipeline

Resume a paused pipeline

validate_pipeline

Validate a pipeline definition

See how to talk to your AI agent using Goldsky (Web3 Data Indexing & Subgraphs).

List all my active Goldsky pipelines.

I've retrieved your pipelines. You have 3 active: 'eth-mainnet-swaps', 'polygon-nft-events', and 'base-bridge-monitor'. Which one would you like to inspect?

Check the status and error count for the pipeline 'eth-mainnet-swaps'.

The pipeline 'eth-mainnet-swaps' is currently 'RUNNING'. I detected 0 errors in the last time window. Everything looks healthy.

Show me the recent logs for the 'polygon-nft-events' pipeline.

Fetching logs for 'polygon-nft-events'... [INFO] Successfully indexed block 5420123... [INFO] Processed 12 Transfer events... [DEBUG] Sink connection stable.

Yes! Use the `validate_pipeline` tool with your definition object. It will check your sources, transforms, and sinks for errors without actually starting a new pipeline.

Related Connectors